Wireless Wearable Multisensory Suite and Real-Time Prediction of Sleep Apnea Episodes
Obstructive sleep apnea (OSA) is a common sleep disorder found in 24% of adult men and 9% of adult women. Although continuous positive airway pressure (CPAP) has emerged as a standard therapy for OSA, a majority of patients are not tolerant to this treatment due to the uncomfortable nasal air delivery during their sleep. We introduce a Dirichlet process-based mixture Gaussian process (DPMG) model to predict the onset of sleep apnea episodes based on analyzing complex cardiorespiratory signals gathered from a custom-designed wireless wearable multisensory suite. Extensive testing with signals from the multisensory suite as well as PhysioNet’s OSA database suggests that the accuracy of offline OSA classification is 88%. Accuracy for predicting an OSA episode 1-min ahead is 83% and 3-min ahead is 77%. Such accurate prediction of an impending OSA episode can be used to adaptively adjust CPAP airflow (towards improving the patient’s adherence), or the torso posture (e.g., minor chin adjustments to maintain steady levels of airflow).
View full article
See complete bios of the authors in the full version of this article.
Trung Q. Le
Satish T.S. Bukkapatnam
Prediction and automatic control are smart ways to solve sleep problems in people suffering from Obstructive Sleep Apnea. However, most predictive methods fail to consider real-world scenarios, such as when one of the sensors in the multi-sensor suite fails. This can easily happen if one is using a pulse oximeter in the sensor system to measure one’s heart rate. Will the predictive method be robust enough to handle such challenges? However, the approach in this paper is feasible and holds significant potential to advance the field and make an important clinical impact.
This article appeared in the 2013 issue of IEEE Journal of Translational Engineering in Health and Medicine.
View all articles on IEEE Xplore